r"""Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distributi

r"""Returns the mean of the scalars that were accumulated for the given statistic between the last two calls to `update()`, or NaN if

Wrapper for the underlying `conv2d()` and `conv_transpose2d()` implementations.

Flush, close possible files, and remove stdout/stderr mirroring.

Build pretrained InceptionV3 Parameters ---------- output_blocks : list of int Indices of blocks to return feature

Build pretrained InceptionV3 Parameters ---------- output_blocks : list of int Indices of blocks to return feature

Flush written text to both stdout and a file, if open.

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

r"""Returns the raw moments that were accumulated for the given statistic between the last two calls to `update()`, or zero if no scal

Calculates the gradient penalty loss for WGAN GP

Traverses the object name and returns the last (rightmost) python object.

r"""Copies current values of the internal counters to the user-visible state and resets them for the next round. If `keep_previous=Tr

r"""Pad, upsample, filter, and downsample a batch of 2D images. Performs the following sequence of operations for each channel: 1. Upsample

Write text to stdout (and a file) and optionally flush.

Prepares inception net for batched usage and returns pool_3 layer.

Fast CUDA implementation of `upfirdn2d()` using custom ops.

Searches for the underlying module behind the name to some python object. Returns the module and the object name (original name with module part r

r"""Test whether the given object or class is persistent, i.e., whether it will save its source code when pickled.

r"""Returns the names of all statistics broadcasted so far that match the regular expression specified at construction time.

r"""Returns the standard deviation of the scalars that were accumulated for the given statistic between the last two calls to `update(

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

private helper for setting up the files_list :return: files => list of paths of files

private helper for setting up the files_list :return: files => list of paths of files

Fast CUDA implementation of `bias_act()` using custom ops.

Slow reference implementation of `bias_act()` using standard TensorFlow ops.

r"""Check that the given object is pickleable, raising an exception if it is not. This function is expected to be considerably more efficient

Returns a the `torch.no_grad` context manager for PyTorch version >= 0.4, or a no-op context manager otherwise.

r"""Query the source code of a given Python module.

r"""Get or create a Python module for the given source code.

r"""Synchronize the global cumulative counters across devices and processes. Called internally by `Collector.update()`.

Slow reference implementation of `upfirdn2d()` using standard PyTorch ops.

Calculation of the statistics used by the FID. Params: -- images : Numpy array of dimension (n_images, hi, wi, 3). The values